# Nextgentic — robots policy. THE single robots source (KIG-1.6, P10).
# Rationale and the Dec-2025 GPTBot/OAI-SearchBot note: docs/geo/bot-policy.md.
# Never add app/robots.ts or any second robots source. Never add a WAF/CDN rule
# that 403/429s a verified retrieval bot.

# --- Default: every crawler. Content is open; private surfaces are closed. ---
User-agent: *
Disallow: /app/
Disallow: /account/
Disallow: /api/
Disallow: /admin/

# --- Answer-engine / search retrieval bots: explicitly allowed to crawl
#     content (they drive GEO visibility), private surfaces still closed. ---
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Googlebot
User-agent: bingbot
User-agent: Applebot
Allow: /
Disallow: /app/
Disallow: /account/
Disallow: /api/
Disallow: /admin/

# --- AI training crawlers: disallowed entirely (no retrieval/citation value). ---
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: Bytespider
Disallow: /

# Canonical origin — keep in sync with content/site.ts (site.origin).
# The sitemap is sharded by content type (app/sitemap.ts, generateSitemaps), so
# Next serves /sitemap/<id>.xml and publishes NO index at /sitemap.xml. Each
# shard is listed here; multiple Sitemap directives are valid per the protocol.
# Adding a content type adds a shard — tests/unit/robots.sitemap.test.ts fails
# until it is listed below.
Sitemap: https://nextgentic.de/sitemap/0.xml
Sitemap: https://nextgentic.de/sitemap/1.xml
Sitemap: https://nextgentic.de/sitemap/2.xml
Sitemap: https://nextgentic.de/sitemap/3.xml
Sitemap: https://nextgentic.de/sitemap/4.xml
Sitemap: https://nextgentic.de/sitemap/5.xml

# LLM-readable site index (llms.txt spec).
# https://nextgentic.de/llms.txt